tf.train.cosine_decay_restarts

View source on GitHub

Applies cosine decay with restarts to the learning rate.

tf.train.cosine_decay_restarts(
    learning_rate, global_step, first_decay_steps, t_mul=2.0, m_mul=1.0, alpha=0.0,
    name=None
)

See [Loshchilov & Hutter, ICLR2016], SGDR: Stochastic Gradient Descent with Warm Restarts. https://arxiv.org/abs/1608.03983

When training a model, it is often recommended to lower the learning rate as the training progresses. This function applies a cosine decay function with restarts to a provided initial learning rate. It requires a global_step value to compute the decayed learning rate. You can just pass a TensorFlow variable that you increment at each training step.

The function returns the decayed learning rate while taking into account possible warm restarts. The learning rate multiplier first decays from 1 to alpha for first_decay_steps steps. Then, a warm restart is performed. Each new warm restart runs for t_mul times more steps and with m_mul times smaller initial learning rate.

Example usage:

first_decay_steps = 1000
lr_decayed = cosine_decay_restarts(learning_rate, global_step,
                                   first_decay_steps)

Eager Compatibility

When eager execution is enabled, this function returns a function which in turn returns the decayed learning rate Tensor. This can be useful for changing the learning rate value across different invocations of optimizer functions.